abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Enumerate meaningful values/levels for a dimension or factor. Mode controls representative, experimental, boundary, pathological, or adversarial coverage.
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill enumerate-dimension-values --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/enumerate-dimension-valuesContext preview
The summary Claude sees to decide when to auto-load this skill.
Enumerate meaningful values/levels for a dimension or factor. Mode controls representative, experimental, boundary, pathological, or adversarial coverage.
name: enumerate-dimension-values description: "Enumerate meaningful values/levels for a dimension or factor. Mode controls representative, experimental, boundary, pathological, or adversarial coverage."
Enumerate meaningful values or levels for a dimension or factor, including representative, experimental, boundary, pathological, or adversarial coverage.
required: [dimensions, value_schema, mode] optional: [ranges, spacing_strategy, domain_constraints, baseline_values] constraints: [values are typed to the dimension; mode determines representative, experimental, boundary, pathological, or adversarial coverage]
1. Validate each dimension's type, range, units, and constraints. 2. Generate representative values and caller-requested boundary or extreme values. 3. For experimental mode, apply the supplied spacing strategy and preserve factor comparability. 4. Deduplicate and annotate rationale, provenance, and expected coverage. 5. Return the value set per dimension.
If the dimension values are ready for controlled combination, consider `construct-design-matrix` as the next tactic. If the values define plausible perturbations around a conclusion, consider `assess-sensitivity` as the next tactic.
produces: [dimension_value_sets, boundary_cases, spacing_annotations, coverage_rationale] delta_fields: [findings, evidence_updates, decisions, uncertainties]
The caller must provide dimensions and types, valid ranges and units, enumeration mode, spacing strategy, baseline values, and domain constraints. If experimental mode is used, provide factor roles and the intended comparison design.
Reject values outside declared domains, levels without units or semantics, or pathological cases presented as representative defaults.
| source | physical line | kind | source criterion | |---|---:|---|---| | creative-ideation/value-enumeration | 11 | numeric | Enumerate 3-5 values per parameter, including extremes. | | experiment-execution/level-specification | 12 | numeric | Experimental factor levels use 2-5 levels and an explicit spacing strategy. |
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target, escalation depth,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.